Patent · US Active

Convolutional neural network on-chip learning system based on non-volatile memory

US11861489B2 · kind B2 · utility

1Cited by

1References

5Claims

0Family size

Assignee

Huazhong University of Science and Technology · CN

Inventors

Xiangshui Miao · Hubei, CN
Yi Li · Hsinchu, TW
Wenqian Pan · Hubei, CN

Key dates

Filing date	Jul 12, 2019
Grant date	Jan 2, 2024
Priority date	—
Expiry date	Oct 29, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/09
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Disclosed by the disclosure is a convolutional neural network on-chip learning system based on non-volatile memory, comprising: an input module, a convolutional neural network module, an output module and a weight update module. The on-chip learning of the convolutional neural network module implements the synaptic function by using the characteristic of the memristor, and the convolutional kernel value or synaptic weight value is stored in a memristor unit; the input module converts the input signal into the voltage signal; the convolutional neural network module converts the input voltage signal layer-by-layer, and transmits the result to the output module to obtain the output of the network; and the weight update module adjusts the conductance value of the memristor in the convolutional neural network module according to the result of the output module to update the network convolutional kernel value or synaptic weight value.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.